Gaussian Process-Based Feature Selection for Wavelet Parameters: Predicting Acute Hypotensive Episodes from Physiological Signals.
Franck DernoncourtKalyan VeeramachaneniUna-May O'ReillyPublished in: CBMS (2015)
Keyphrases
- gaussian process
- hyperparameters
- physiological signals
- feature selection
- model selection
- gaussian processes
- bayesian framework
- latent variables
- regression model
- support vector
- feature extraction
- cross validation
- semi supervised
- maximum likelihood
- multi task
- parameter settings
- emotion recognition
- expectation propagation
- closed form
- human subjects
- text classification
- heart rate
- multiscale
- wavelet coefficients
- generative model
- em algorithm
- bayesian inference
- random sampling
- denoising
- information extraction
- probabilistic model
- data streams
- data sets